Models & Labs
llama.cpp adds Snapdragon Hexagon NPU builds
llama.cpp Releaseshigh confidence
Why it matters
- →Snapdragon Hexagon NPU binaries are now officially available in release assets.
- →Enables efficient local inference on Qualcomm-based ARM devices without custom builds.
- →Maintains support for latest CUDA 13 and ROCm 10.0 desktop GPU stacks.
llama.cpp has updated its release workflow to include Snapdragon builds, providing binaries for CPU, Adreno GPU, and Hexagon NPU on Linux arm64. This change addresses a previous limitation where these builds were only used for internal CI testing. The update also includes standard support for CUDA 12/13, ROCm 10.0, and various other hardware accelerators across macOS, Windows, and Linux platforms.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
What happened next
- 1llama.cpp b11146 adds CUDA 13 and Snapdragon support
llama.cpp Releases · September 24, 2026 · Same story
- 2llama.cpp b12032 adds CUDA 13 and Snapdragon support
llama.cpp Releases · November 1, 2026 · Same story
Follow this story
Open the full story →llama.cpp b11054 adds Hexagon TOP_K support
3 developments
- Sep 20 · llama.cpp Releases
llama.cpp b11054 adds Hexagon TOP_K support - Sep 22 · llama.cpp Releases
llama.cpp adds Snapdragon Hexagon NPU builds (This article) - Sep 22 · llama.cpp Releases
llama.cpp b11095 optimizes Hexagon and adds ROCm 10
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
llama.cpp Releases
Models & Labscoding
llama.cpp b12342 adds few-row MMQ for speculative decoding
Speculative decoding just got a significant speed boost on NVIDIA GPUs. This release introduces a specialized kernel for 'few-row' matrix multiplications, targeting the small batch sizes typical of verification passes in speculative decoding workflows. By optimizing these specific operations for quantized formats like Q8_0 and IQ4 variants, llama.cpp reduces latency where it matters most during token generation. The change is CUDA-only for now but leverages hardware capabilities from Ampere onwards, making local inference faster without requiring new model architectures or complex configuration changes.
llama.cpp Releases
More in Models & Labs
© TechCrunch AIModels & Labsmodels
Google deploys Gemini 4 Hydrogen for faster Search
Google is quietly shifting its search infrastructure by replacing older fast models with Gemini 4 Hydrogen, a tier designed specifically for speed and cost-efficiency rather than raw reasoning power. This model completes tasks 2.5 times faster than its predecessor while beating the more powerful Argon on specific intelligence benchmarks, proving that specialized efficiency can outperform brute force in high-volume workflows. By integrating this into Search's fan-out technique, Google now breaks down complex queries into subqueries with greater precision and speed, delivering richer visual responses without the latency of heavier models. This marks a strategic pivot toward agentic execution layers within consumer search, making AI Mode feel snappier for everyday multi-part questions.
TechCrunch AI
© Hugging Face BlogModels & Labscoding
IBM releases LLMON markup to fix prompt injection
IBM is tackling the brittleness of small language models by introducing LLMON, a structured markup language that explicitly separates instructions from data. By using reserved special tokens instead of ambiguous characters like JSON brackets, these new Granite 4.1 preview models drastically reduce indirect prompt injection attacks while maintaining standard performance. This approach forces the model to bind specific constraints to specific data payloads, eliminating the confusion that often leads to hallucinations or security breaches in long contexts.
Hugging Face Blog
© The AI Daily BriefModels & Labsmodels
Google Releases Gemini 4 Carbon Model
Google has released the Gemini 4 Carbon model, expanding its multimodal AI lineup with new capabilities for developers and users.
The AI Daily Brief